Speaker verification using relaxation labeling

Tuan Pham; Dat Tran; Michael Wagner

Speaker verification using relaxation labeling

Tuan Pham, Dat Tran, Michael Wagner

Information Systems

Research output: Contribution to conference (non-published works) › Paper › peer-review

6 Citations (SciVal)

Abstract

A relaxation algorithm for speaker verification is presented in this paper. This verification system uses a nonlinear probabilistic framework to paralelly and iteratively update the labelings of the input speech feature vectors until no further improvements are found. The implementation is tested on a commercial speech corpus TI46. The equal error rates obtained from the proposed approach are significantly more favorable than those from the conventional VQ-based method.

Original language	English
Pages	29-32
Number of pages	4
Publication status	Published - 2020
Event	Workshop on Speaker Recognition and its Commercial and Forensic Applications, RLA2C 1998 - Avignon, France Duration: 20 Apr 1998 → 23 Apr 1998

Conference

Conference	Workshop on Speaker Recognition and its Commercial and Forensic Applications, RLA2C 1998
Country/Territory	France
City	Avignon
Period	20/04/98 → 23/04/98

Cite this

@conference{c0095dc7300e49abaa548412c275b26d,

title = "Speaker verification using relaxation labeling",

abstract = "A relaxation algorithm for speaker verification is presented in this paper. This verification system uses a nonlinear probabilistic framework to paralelly and iteratively update the labelings of the input speech feature vectors until no further improvements are found. The implementation is tested on a commercial speech corpus TI46. The equal error rates obtained from the proposed approach are significantly more favorable than those from the conventional VQ-based method.",

author = "Tuan Pham and Dat Tran and Michael Wagner",

note = "Publisher Copyright: Copyright {\textcopyright} RLA2C 1998 - Speaker Recognition and its Commercial and Forensic Applications.All rights reserved.; Workshop on Speaker Recognition and its Commercial and Forensic Applications, RLA2C 1998 ; Conference date: 20-04-1998 Through 23-04-1998",

year = "2020",

language = "English",

pages = "29--32",

}

TY - CONF

T1 - Speaker verification using relaxation labeling

AU - Pham, Tuan

AU - Tran, Dat

AU - Wagner, Michael

PY - 2020

Y1 - 2020

N2 - A relaxation algorithm for speaker verification is presented in this paper. This verification system uses a nonlinear probabilistic framework to paralelly and iteratively update the labelings of the input speech feature vectors until no further improvements are found. The implementation is tested on a commercial speech corpus TI46. The equal error rates obtained from the proposed approach are significantly more favorable than those from the conventional VQ-based method.

AB - A relaxation algorithm for speaker verification is presented in this paper. This verification system uses a nonlinear probabilistic framework to paralelly and iteratively update the labelings of the input speech feature vectors until no further improvements are found. The implementation is tested on a commercial speech corpus TI46. The equal error rates obtained from the proposed approach are significantly more favorable than those from the conventional VQ-based method.

UR - http://www.scopus.com/inward/record.url?scp=34548112132&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:34548112132

SP - 29

EP - 32

T2 - Workshop on Speaker Recognition and its Commercial and Forensic Applications, RLA2C 1998

Y2 - 20 April 1998 through 23 April 1998

ER -

Speaker verification using relaxation labeling

Abstract

Conference

Other files and links

Fingerprint

Cite this